|
Title
|
|
|
|
Fast tomographic reconstruction from highly limited data using artificial neural networks
| |
|
Author
|
|
|
|
| |
|
Abstract
|
|
|
|
| Obtaining accurate reconstructions from a small num ber of projections is important in many tomographic applications. Current advanced reconstruction metho ds are able to produce accurate reconstructions in some cases, but they are usually computationally ex pensive. Here, we present a reconstruction method based on artificial neural networks, which can be v iewed as a combination of fast filtered backproject ion reconstructions. Since the method learns characteri stics of scanned objects during the training phase, it is able to reconstruct images accurately from limited data. Results from experimental μ CT data show that the new method is able to produce more accurate rec onstructions than both regular filtered backproject ion and the slower iterative SIRT method, while having a relatively low computational cost. |
| |
|
Language
|
|
|
|
English
| |
|
Source (book)
|
|
|
|
1st International Conference on Tomography of Materials and Structures (ICTMS), Ghent, Belgium
| |
|
Publication
|
|
|
|
2013
| |
|
Volume/pages
|
|
|
|
(2013)
, p. 109-112
| |
|
Full text (open access)
|
|
|
|
| |
|